METHOD FOR TRAINING AN ARTIFICIAL NEURAL NETWORK COMPRISING QUANTIZED PARAMETERS - Patent 4150531

(19)

(11)

EP 4 150 531 A1

(12)

(43)	Date of publication:
	22.03.2023 Bulletin 2023/12

(21)	Application number: 20767887.1

(22)	Date of filing: 03.06.2020

(51)

International Patent Classification (IPC):

G06N 3/08^(2006.01)

(52)	Cooperative Patent Classification (CPC):
	G06N 3/08

(86)	International application number:
	PCT/RU2020/000263

(87)	International publication number:
	WO 2021/246892 (09.12.2021 Gazette 2021/49)

(84)	Designated Contracting States:
	AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
	Designated Extension States:
	BA ME
	Designated Validation States:
	KH MA MD TN

(71)	Applicant: Huawei Technologies Co., Ltd.
	Longgang District, Shenzhen, Guangdong 518129 (CN)

(72)	Inventors:
	CHIKIN, Vladimir Maximovich Shenzhen Guangdong, 518129 (CN) TELEGINA, Anna Dmitrievna Shenzhen Guangdong, 518129 (CN) GLUKHOV, Valery Nikolaevich Shenzhen Guangdong, 518129 (CN) SOLODSKIKH, Kirill Igorevich Shenzhen Guangdong, 518129 (CN)

(74)	Representative: Gill Jennings & Every LLP
	The Broadgate Tower 20 Primrose Street London EC2A 2ES London EC2A 2ES (GB)

(54)	METHOD FOR TRAINING AN ARTIFICIAL NEURAL NETWORK COMPRISING QUANTIZED PARAMETERS